Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 772 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.4946. Min Act: -0.1700

Data Index: 8124169 (Open Web Text)

Max Activating Token Index: 940

Text #1

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.5041. Min Act: -0.1700

Data Index: 1708188 (Open Web Text)

Max Activating Token Index: 425

Text #2

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.4867. Min Act: -0.1700

Data Index: 7784087 (Open Web Text)

Max Activating Token Index: 174

Text #3

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.3969. Min Act: -0.1700

Data Index: 8780429 (Open Web Text)

Max Activating Token Index: 636

Text #4

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.4190. Min Act: -0.1700

Data Index: 3598475 (Open Web Text)

Max Activating Token Index: 452

Text #5

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.4018. Min Act: -0.1700

Data Index: 4903693 (Open Web Text)

Max Activating Token Index: 327

Text #6

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.3525. Min Act: -0.1700

Data Index: 7945526 (Open Web Text)

Max Activating Token Index: 633

Text #7

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.3758. Min Act: -0.1700

Data Index: 1342169 (Open Web Text)

Max Activating Token Index: 817

Text #8

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.3913. Min Act: -0.1700

Data Index: 8780385 (Open Web Text)

Max Activating Token Index: 317

Text #9

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.3519. Min Act: -0.1700

Data Index: 8397986 (Open Web Text)

Max Activating Token Index: 927

Text #10

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.3765. Min Act: -0.1700

Data Index: 5607502 (Open Web Text)

Max Activating Token Index: 731

Text #11

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.3788. Min Act: -0.1700

Data Index: 4713804 (Open Web Text)

Max Activating Token Index: 440

Text #12

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.3499. Min Act: -0.1700

Data Index: 6106433 (Open Web Text)

Max Activating Token Index: 68

Text #13

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.3464. Min Act: -0.1700

Data Index: 2941223 (Open Web Text)

Max Activating Token Index: 713

Text #14

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.3413. Min Act: -0.1700

Data Index: 3944497 (Open Web Text)

Max Activating Token Index: 62

Text #15

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.3442. Min Act: -0.1700

Data Index: 1875082 (Open Web Text)

Max Activating Token Index: 687

Text #16

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.3116. Min Act: -0.1700

Data Index: 3074385 (Open Web Text)

Max Activating Token Index: 694

Text #17

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.3010. Min Act: -0.1700

Data Index: 4815491 (Open Web Text)

Max Activating Token Index: 601

Text #18

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.3040. Min Act: -0.1700

Data Index: 6903681 (Open Web Text)

Max Activating Token Index: 310

Text #19

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.2809. Min Act: -0.1700

Data Index: 3737883 (Open Web Text)

Max Activating Token Index: 827